From 5c33677c87cbe44ae04df69c4a29c1750a9ec4e5 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Tue, 11 Oct 2016 15:16:57 +0100 Subject: [PATCH 1/7] dm raid: fix compat_features validation In ecbfb9f118bce4 ("dm raid: add raid level takeover support") a new compatible feature flag was added. Validation for these compat_features was added but this only passes for new raid mappings with this feature flag. This causes previously created raid mappings to be failed at import. Check compat_features for the only valid combination. Fixes: ecbfb9f118bce4 ("dm raid: add raid level takeover support") Cc: stable@vger.kernel.org # v4.8 Signed-off-by: Andy Whitcroft Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-raid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 8abde6b8cedc..2a3970097991 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2258,7 +2258,8 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) if (!mddev->events && super_init_validation(rs, rdev)) return -EINVAL; - if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) { + if (le32_to_cpu(sb->compat_features) && + le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) { rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags"; return -EINVAL; } From dcb2ff56417362c31f6b430c3c531a84581e8721 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Mon, 10 Oct 2016 17:58:32 +0200 Subject: [PATCH 2/7] dm mirror: fix read error on recovery after default leg failure If a default leg has failed, any read will cause a new operational default leg to be selected and the read is resubmitted. But until now the read will return failure even though it was successful due to resubmission. The reason for this is bio->bi_error was not being cleared before resubmitting the bio. Fix by clearing bio->bi_error before resubmission. Fixes: 4246a0b63bd8 ("block: add a bi_error field to struct bio") Cc: stable@vger.kernel.org # 4.3+ Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-raid1.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index bdf1606f67bc..7a6254d54baf 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1292,6 +1292,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) dm_bio_restore(bd, bio); bio_record->details.bi_bdev = NULL; + bio->bi_error = 0; queue_bio(ms, bio, rw); return DM_ENDIO_INCOMPLETE; From 12a7cf5ba6c776a2621d8972c7d42e8d3d959d20 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Mon, 10 Oct 2016 18:48:06 +0200 Subject: [PATCH 3/7] dm mirror: use all available legs on multiple failures When any leg(s) have failed, any read will cause a new operational default leg to be selected and the read is resubmitted to it. If that new default leg fails the read too, no other still accessible legs are used to resubmit the read again -- thus failing the io. Fix by allowing the read to get resubmitted until all operational legs have been exhausted. Also, remove any details.bi_dev use as a flag. Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-raid1.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 7a6254d54baf..9a8b71067c6e 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -145,7 +145,6 @@ static void dispatch_bios(void *context, struct bio_list *bio_list) struct dm_raid1_bio_record { struct mirror *m; - /* if details->bi_bdev == NULL, details were not saved */ struct dm_bio_details details; region_t write_region; }; @@ -1200,8 +1199,6 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) struct dm_raid1_bio_record *bio_record = dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record)); - bio_record->details.bi_bdev = NULL; - if (rw == WRITE) { /* Save region for mirror_end_io() handler */ bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio); @@ -1260,22 +1257,12 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) } if (error == -EOPNOTSUPP) - goto out; + return error; if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD)) - goto out; + return error; if (unlikely(error)) { - if (!bio_record->details.bi_bdev) { - /* - * There wasn't enough memory to record necessary - * information for a retry or there was no other - * mirror in-sync. - */ - DMERR_LIMIT("Mirror read failed."); - return -EIO; - } - m = bio_record->m; DMERR("Mirror read failed from %s. Trying alternative device.", @@ -1291,7 +1278,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) bd = &bio_record->details; dm_bio_restore(bd, bio); - bio_record->details.bi_bdev = NULL; bio->bi_error = 0; queue_bio(ms, bio, rw); @@ -1300,9 +1286,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) DMERR("All replicated volumes dead, failing I/O"); } -out: - bio_record->details.bi_bdev = NULL; - return error; } From b052b07c39d593c9954a84d5bbe1563999483f38 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Mon, 17 Oct 2016 21:20:07 +0200 Subject: [PATCH 4/7] dm raid: fix activation of existing raid4/10 devices dm-raid 1.9.0 fails to activate existing RAID4/10 devices that have the old superblock format (which does not have takeover/reshaping support that was added via commit 33e53f06850f). Fix validation path for old superblocks by reverting to the old raid4 layout and basing checks on mddev->new_{level,layout,...} members in super_init_validation(). Cc: stable@vger.kernel.org # 4.8 Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- Documentation/device-mapper/dm-raid.txt | 1 + drivers/md/dm-raid.c | 12 +++++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index e5b6497116f4..c75b64a85859 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -309,3 +309,4 @@ Version History with a reshape in progress. 1.9.0 Add support for RAID level takeover/reshape/region size and set size reduction. +1.9.1 Fix activation of existing RAID 4/10 mapped devices diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 2a3970097991..6d53810963f7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -266,7 +266,7 @@ static struct raid_type { {"raid10_offset", "raid10 offset (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_OFFSET}, {"raid10_near", "raid10 near (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_NEAR}, {"raid10", "raid10 (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_DEFAULT}, - {"raid4", "raid4 (dedicated last parity disk)", 1, 2, 4, ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */ + {"raid4", "raid4 (dedicated first parity disk)", 1, 2, 5, ALGORITHM_PARITY_0}, /* raid4 layout = raid5_0 */ {"raid5_n", "raid5 (dedicated last parity disk)", 1, 2, 5, ALGORITHM_PARITY_N}, {"raid5_ls", "raid5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC}, {"raid5_rs", "raid5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC}, @@ -2087,11 +2087,11 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) /* * No takeover/reshaping, because we don't have the extended v1.9.0 metadata */ - if (le32_to_cpu(sb->level) != mddev->level) { + if (le32_to_cpu(sb->level) != mddev->new_level) { DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)"); return -EINVAL; } - if (le32_to_cpu(sb->layout) != mddev->layout) { + if (le32_to_cpu(sb->layout) != mddev->new_layout) { DMERR("Reshaping raid sets not yet supported. (raid layout change)"); DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout); DMERR(" Old layout: %s w/ %d copies", @@ -2102,7 +2102,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) raid10_md_layout_to_copies(mddev->layout)); return -EINVAL; } - if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) { + if (le32_to_cpu(sb->stripe_sectors) != mddev->new_chunk_sectors) { DMERR("Reshaping raid sets not yet supported. (stripe sectors change)"); return -EINVAL; } @@ -2115,6 +2115,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) return -EINVAL; } + DMINFO("Discovered old metadata format; upgrading to extended metadata format"); + /* Table line is checked vs. authoritative superblock */ rs_set_new(rs); } @@ -3647,7 +3649,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 9, 0}, + .version = {1, 9, 1}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, From d09960b0032174eb493c4c13be5b9c9ef36dc9a7 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Mon, 10 Oct 2016 05:35:19 -0700 Subject: [PATCH 5/7] dm: free io_barrier after blk_cleanup_queue call dm_old_request_fn() has paths that access md->io_barrier. The party destroying io_barrier should ensure that no future execution of dm_old_request_fn() is possible. Move io_barrier destruction to below blk_cleanup_queue() to ensure this and avoid a NULL pointer crash during request-based DM device shutdown. Cc: stable@vger.kernel.org # 4.3+ Signed-off-by: Tahsin Erdogan Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index be35258324c1..ec513ee864f2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1423,8 +1423,6 @@ static void cleanup_mapped_device(struct mapped_device *md) if (md->bs) bioset_free(md->bs); - cleanup_srcu_struct(&md->io_barrier); - if (md->disk) { spin_lock(&_minor_lock); md->disk->private_data = NULL; @@ -1436,6 +1434,8 @@ static void cleanup_mapped_device(struct mapped_device *md) if (md->queue) blk_cleanup_queue(md->queue); + cleanup_srcu_struct(&md->io_barrier); + if (md->bdev) { bdput(md->bdev); md->bdev = NULL; From 937fa62e8a00d0b4bc2c0a40567d7c88ab2b2e8d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 18 Oct 2016 14:02:04 -0400 Subject: [PATCH 6/7] dm rq: clear kworker_task if kthread_run() returned an error cleanup_mapped_device() calls kthread_stop() if kworker_task is non-NULL. Currently the assigned value could be a valid task struct or an error code (e.g -ENOMEM). Reset md->kworker_task to NULL if kthread_run() returned an erorr. Fixes: 7193a9defc ("dm rq: check kthread_run return for .request_fn request-based DM") Cc: stable@vger.kernel.org # 4.8 Reported-by: Tahsin Erdogan Signed-off-by: Mike Snitzer --- drivers/md/dm-rq.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 5eacce1ef88b..63e43f261cce 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -856,8 +856,11 @@ int dm_old_init_request_queue(struct mapped_device *md) init_kthread_worker(&md->kworker); md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker, "kdmwork-%s", dm_device_name(md)); - if (IS_ERR(md->kworker_task)) - return PTR_ERR(md->kworker_task); + if (IS_ERR(md->kworker_task)) { + int error = PTR_ERR(md->kworker_task); + md->kworker_task = NULL; + return error; + } elv_register_queue(md->queue); From dafa724bf582181d9a7d54f5cb4ca0bf8ef29269 Mon Sep 17 00:00:00 2001 From: "tang.junhui" Date: Fri, 21 Oct 2016 09:35:32 +0800 Subject: [PATCH 7/7] dm table: fix missing dm_put_target_type() in dm_table_add_target() dm_get_target_type() was previously called so any error returned from dm_table_add_target() must first call dm_put_target_type(). Otherwise the DM target module's reference count will leak and the associated kernel module will be unable to be removed. Also, leverage the fact that r is already -EINVAL and remove an extra newline. Fixes: 36a0456 ("dm table: add immutable feature") Fixes: cc6cbe1 ("dm table: add always writeable feature") Fixes: 3791e2f ("dm table: add singleton feature") Cc: stable@vger.kernel.org # 3.2+ Signed-off-by: tang.junhui Signed-off-by: Mike Snitzer --- drivers/md/dm-table.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 3e407a9cde1f..c4b53b332607 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -695,37 +695,32 @@ int dm_table_add_target(struct dm_table *t, const char *type, tgt->type = dm_get_target_type(type); if (!tgt->type) { - DMERR("%s: %s: unknown target type", dm_device_name(t->md), - type); + DMERR("%s: %s: unknown target type", dm_device_name(t->md), type); return -EINVAL; } if (dm_target_needs_singleton(tgt->type)) { if (t->num_targets) { - DMERR("%s: target type %s must appear alone in table", - dm_device_name(t->md), type); - return -EINVAL; + tgt->error = "singleton target type must appear alone in table"; + goto bad; } t->singleton = true; } if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) { - DMERR("%s: target type %s may not be included in read-only tables", - dm_device_name(t->md), type); - return -EINVAL; + tgt->error = "target type may not be included in a read-only table"; + goto bad; } if (t->immutable_target_type) { if (t->immutable_target_type != tgt->type) { - DMERR("%s: immutable target type %s cannot be mixed with other target types", - dm_device_name(t->md), t->immutable_target_type->name); - return -EINVAL; + tgt->error = "immutable target type cannot be mixed with other target types"; + goto bad; } } else if (dm_target_is_immutable(tgt->type)) { if (t->num_targets) { - DMERR("%s: immutable target type %s cannot be mixed with other target types", - dm_device_name(t->md), tgt->type->name); - return -EINVAL; + tgt->error = "immutable target type cannot be mixed with other target types"; + goto bad; } t->immutable_target_type = tgt->type; } @@ -740,7 +735,6 @@ int dm_table_add_target(struct dm_table *t, const char *type, */ if (!adjoin(t, tgt)) { tgt->error = "Gap in table"; - r = -EINVAL; goto bad; }